sys.path.insert(0, LIB)
import matplotlib.pyplot as plt
from Cluster import KMeans as kmeans
from sklearn.cluster import KMeans
import numpy as np
import pandas as pd
trainData = np.array(
pd.read_table(os.path.join(DAT, 'train.txt'),
header=None,
encoding='gb2312',
delim_whitespace=True))
trainData = np.array(trainData)
time_start1 = time.time()
clf1 = kmeans(k=4, cluster_type="KMeans")
pred1 = clf1.train(trainData)
time_end1 = time.time()
print("Runtime of KMeans:", time_end1 - time_start1)
time_start2 = time.time()
clf2 = kmeans(k=4, cluster_type="biKMeans")
pred = clf2.train(trainData)
time_end2 = time.time()
print("Runtime of biKMeans:", time_end2 - time_start2)
time_start3 = time.time()
clf3 = kmeans(k=4, cluster_type="KMeans++")
pred3 = clf3.train(trainData)
time_end3 = time.time()
print("Runtime of KMeans++:", time_end3 - time_start3)
# LIB is the parent directory of the directory where program resides.
LIB = os.path.join(os.path.dirname(__file__), '..')
DAT = os.path.join(os.path.dirname(__file__), '..', 'dataset', 'dataset2')
sys.path.insert(0, LIB)
from Cluster import KMeans as kmeans
from Cluster import DBSCAN as dbscan
from sklearn.cluster import DBSCAN
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import datasets
X1, y1 = datasets.make_circles(n_samples=5000, factor=.6, noise=.05)
trainData = X1[0:1000]
time_start1 = time.time()
clf1 = kmeans(k=4, cluster_type="KMeans")
pred1 = clf1.train(trainData)
time_end1 = time.time()
print("Runtime of KMeans:", time_end1 - time_start1)
time_start2 = time.time()
clf2 = dbscan()
pred = clf2.train(trainData)
time_end2 = time.time()
print("Runtime of DBSCAN:", time_end2 - time_start2)
time_start3 = time.time()
clf3 = DBSCAN(eps=0.1, min_samples=10)
clf3.fit(trainData)
pred3 = clf3.labels_
time_end3 = time.time()